transcription

The `transcribe` Module

The transcribe module takes audio input and returns a text transcript of all words spoken therein.

This overview of the transcribe module is divided into the following sections:

Inputs and Outputs of the transcribe Module
Available Models in the transcribe Module
Model Parameters in the transcribe Module
Input File Size Limit
A Single-Module Pipeline for the transcribe Module
Further Information on transcribe Module IO and Clickability

Inputs and Outputs of the `transcribe` Module

The transcribe module accepts audio inputs. Acceptable file formats are the following:

MP3

The transcribe module returns a JSON file. The returned JSON file has all snippets of transcribed text, and along with each includes timestamps and a "confidence" value for the accuracy of each transcription.

Available Models in the `transcribe` Module

You can activate any of the following models when using the transcribe module:

whisper-tiny - (default) Most cost-effective and least accurate of the Whisper models [99 languages, see model card]
whisper-base [99 languages, see model card]
whisper-small [99 languages, see model card]
whisper-medium [99 languages, see model card]
whisper-large-v3 - Most accurate but most expensive to run of the Whisper models [99 languages, see model card]

Use the modules argument in the process method to determine what model you'd like active when you process files through the transcribe module.

Model Parameters in the `transcribe` Module

None of the transcribe module models are parameterizable. Consequently, when selecting what model you'll use through the process method's modules argument, params will always be set to an empty dictionary. For example:

# example model selection for transcribe module in process
modules={'transcribe': {'model':'whisper-small',
                       'params': {}}}

Input File Size Limit

transcribe module input audio files can currently be no larger than 3MB.

A Single-Module Pipeline for the `transcribe` Module

Please click here to visit the Pipeline Examples section of our documentation and review an example of a single-module pipeline for the transcribe module.

Further Information on `transcribe` Module IO and Clickability

Please click here to visit the Convenience Methods (and More!) documentation. There you will find two tools to learn more about the transcribe module:

transcription

The transcribe Module

Inputs and Outputs of the transcribe Module

Available Models in the transcribe Module

Model Parameters in the transcribe Module